Affective and behavioural computing: Lessons learnt from the First Computational Paralinguistics Challenge

•Review of the first Interspeech Challenge that actually ran under the label of Interspeech ComParE – the broadest to date – and the larger field.•Original fusion results of the best winning systems to establish a new baseline.•Additional novel analyses such as average confusion matrices of the participant’s systems.•Novel single feature baselines.•In-depth discussion of the performance variation and algorithms used. In this article, we review the INTERSPEECH 2013 Computational Paralinguistics ChallengE (ComParE) – the first of its kind– in light of the recent developments in affective and behavioural computing. The impact of the first ComParE instalment is manifold: first, it featured various new recognition tasks including social signals such as laughter and fillers, conflict in dyadic group discussions, and atypical communication due to pervasive developmental disorders, as well as enacted emotion; second, it marked the onset of the ComParE, subsuming all tasks investigated hitherto within the realm of computational paralinguistics; finally, besides providing a unified test-bed under well-defined and strictly comparable conditions, we present the definite feature vector used for computation of the baselines, thus laying the foundation for a successful series of follow-up Challenges. Starting with a review of the preceding INTERSPEECH Challenges, we present the four Sub-Challenges of ComParE 2013. In particular, we provide details of the Challenge databases and a meta-analysis by conducting experiments of logistic regression on single features and evaluating the performances achieved by the participants.